Synonym discovery method and device, data processing method and device
A discovery method and technology of synonyms, applied in the field of data processing, can solve the problems of identifying acronyms and low accuracy of semantic understanding, and achieve the effect of improving accuracy and efficiency
Active Publication Date: 2018-12-28
SHANGHAI XIAOI ROBOT TECH CO LTD
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the synonym discovery methods in the prior art cannot recognize acronyms well, so that the accuracy of semantic understanding is low
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] Abbreviations of proper names often appear in Chinese writing and daily expressions. These abbreviated words are called abbreviations of proper names. Abbreviations are part of the original proper names, and abbreviations are also a type of synonyms. For example, "National People's Congress" is an acronym for "National People's Congress", "China" is an abbreviation for "People's Republic of China", "Real Madrid" is an abbreviation for "Real Madrid" and so on. However, the synonym discovery methods in the prior art cannot identify acronyms well, resulting in lower accuracy of semantic understanding.
[0045] This embodiment of the present invention obtains a set of phrases to be processed; for any word to be processed in the set of phrases, when there are one or more target words in the set of phrases, the relationship between the to-be-processed word and the target word is ensured. When the minimum edit distance is less than the preset threshold, the word to be processed ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a synonym discovery method and device as well as a data processing method and device. The synonym discovery method comprises the following steps of: obtaining a to-be-processed word group set, wherein the word group set comprises a plurality of words; and for any to-be-processed word in the word group set, when one or more target words exist in the word group set and the minimum edition distance from the to-be-processed word to the target words is smaller than a preset threshold value, determining a target word corresponding to the to-be-processed word as a synonym word pair, wherein the minimum edition distance is calculated through an edition distance method, the edition distance method comprises a deletion operation, an edition distance corresponding to the deletion operation is smaller than edition distances corresponding to other operations, the edition distance corresponding to the deletion operation is greater than the preset threshold value, and the edition distance of each of the other operations is greater than or equal to the preset threshold value. Through above scheme, the correctness of discovering abbreviations can be improved.
Description
technical field [0001] The present invention relates to the field of data processing, in particular to a method and device for finding synonyms, and a method and device for processing data. Background technique [0002] Synonymous relationship is a very important semantic relationship, which is often used in natural language processing tasks such as information retrieval and text classification. Specifically, before processing tasks such as information retrieval or text classification, it is necessary to obtain synonyms and identify synonyms. For example, in the application scenario of information retrieval, multiple words belonging to synonyms can be classified into one category. When there are keywords with synonyms in the input text, the synonyms can be used instead of the original keywords to search, so that the retrieval system can Provide the user with more text to confirm. [0003] Abbreviations of proper names often appear in Chinese writing and daily expressions. ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/27
CPCG06F40/247
Inventor 张昊朱频频
Owner SHANGHAI XIAOI ROBOT TECH CO LTD